Models & Labs
FLUX.3 Image Klein arrives in Diffusers
Hugging Face Bloghigh confidence
Why it matters
- →Native Diffusers support removes integration friction for developers using FLUX.3.
- →The distilled checkpoint offers exceptional speed (~2s on H100) for high-resolution generation.
- →Modular architecture and quantization options enable deployment on consumer-grade GPUs.
Black Forest Labs has released its FLUX.3 Image Klein model weights to the Hugging Face Diffusers library, providing native support for both base and distilled checkpoints. The distilled variant generates 1024x1024 images in approximately two seconds on NVIDIA H100 hardware, while supporting NVFP4 and FP8 quantization for lower-memory deployment. The release includes a modular pipeline architecture that facilitates text-to-image, multi-reference image-to-image, and bounding-box layout control tasks. Developers can now utilize official LoRA training scripts for both generation and editing, integrating the model into existing open-source workflows.
Read originalThe story around this
Earlier coverage that leads up to this article, and what followed. Lines connect each piece to the closest one after it, converging here.
More from Hugging Face Blog
More in Models & Labs
Models & Labsmodels
llama.cpp b12029 adds CUDA 13 and Snapdragon support
This release quietly cements llama.cpp as the universal inference runtime by finally supporting NVIDIA's latest CUDA 13 stack alongside AMD's ROCm 10.0. The inclusion of native builds for Linux arm64 with Snapdragon chips, covering CPU, Adreno GPU, and Hexagon NPU, signals a serious push into mobile edge deployment. While Apple Silicon KleidiAI is disabled in this specific build, the broader hardware coverage means developers no longer need to compile from source for most modern accelerators. It’s less about new features and more about removing friction for anyone running local models on bleeding-edge or diverse hardware.
llama.cpp Releases
© The Verge AIModels & Labsother
